OBJECTIVE:Nowadays,machine learning algorithms are gradually being applied to predict stroke and cardiovascular disease.Compared with traditional regression models,machine learning can learn from data to achieve high prediction accuracy by exploring the flexible relationship between a large number of predictive features and outcome variables,providing a new method for the formulation of individualized treatment and rehabilitation programs.This study aims to systematically evaluate stroke functional recovery and prognosis prediction models based on machine learning,comprehensively assessing their predictive performance and clinical application potential to provide references for the development,application,and promotion of related predictive models.METHODS:This review was conducted following the PRISMA(Preferred Reporting Items for Systematic Reviews and Meta-Analyses)guidelines.Relevant literature on stroke prognosis prediction using machine learning methods was selected by searching PubMed,EMbase,Web of Science Core Collection,CNKI,WanFang,and the China Biomedical Literature Database,with the search period from January 1,2014,to July 1,2024.Two researchers independently screened the literature and extracted data based on inclusion and exclusion criteria,using the Prediction model Risk Of Bias ASsessment Tool(PROBAST)to assess model quality.RESULTS:(1)A total of 3 126 articles were obtained in the preliminary search.After screening and exclusion,18 articles were finally included.150 prediction models were constructed using 13 machine learning methods.The three most frequently used methods are Logistic Regression,Random Forest,and Extreme Gradient Boosting(XGBoost).Only one study was externally validated.Eight studies reported how the missing data were handled.(2)In terms of outcome indicators,8 studies used the combination of clinical data and imaging data to build models,9 studies only used clinical data to build models,and 1 study only used imaging data to build models.(3)Each of the 18 studies gave the most important characteristics of the study,with the most mentioned being the National Institute of Health Stroke Scale and age.All studies reported area under curve values ranging from 0.74 to 0.96,with the highest area under curve being 0.96.The overall risk of bias in all models was high.The high risk of bias in the field of model analysis was the main reason for the high risk of overall bias in all models.(4)The results of meta-analysis showed that age and National Institute of Health Stroke Scale score had significant influence on stroke prognosis,with age[MD=8.49,95％CI(6.24,10.75),P＜0.01]and National Institute of Health Stroke Scale score[MD=4.78,95％CI(2.56,7.00),P＜0.01].CONCLUSION:This study systematically evaluated the predictive model of functional recovery and prognosis of stroke based on machine learning,and all the models have good predictive potential.However,future studies should increase the sample size of the included model,adopt prospective studies,and add external validation of the model to improve the stability and prediction accuracy of the model,control the risk of bias,and contribute to the validation and promotion of the model in practical clinical applications.At the same time,the interpolation of missing values is more transparent and accurate.Although existing machine learning models show good predictive performance,it is also important to focus on the functionality and usability of the model,and the inclusion of features will reduce ease of use.We should develop easy to use model interfaces and user-friendly clinical tools to enable medical staff to better apply the model for clinical decision.

Objective:To investigate the significance of urinary 8-oxo-7, 8-dihydroguanosine(8-oxoGuo)in assessing the short-term prognosis of sepsis in frail elderly patients.Methods:We conducted a cross-sectional study involving 62 frail elderly patients diagnosed with sepsis who were admitted to the Emergency Intensive Care Unit(EICU)at Beijing Hospital between March 2021 and March 2022.Based on their 28-day prognosis, the patients were categorized into two groups: those who died and those who survived.Upon admission, we collected urine samples and clinical data from both groups.We employed isotope dilution high-performance liquid chromatography-mass spectrometry to measure the levels of the RNA oxidation marker 8-oxoGuo in the urine.Results:A total of 62 frail elderly patients[aged(85.1±6.3)years]diagnosed with sepsis were included in the study, comprising 36 patients in the 28-day mortality group and 26 patients in the survival group.Univariate analysis revealed that the survival group had significantly lower body temperature, blood calcitonin(PCT)levels, sequential organ failure assessment(SOFA)scores, and urinary 8-oxoGuo levels compared to the mortality group.Additionally, the survival group exhibited a higher mean arterial pressure(MAP)than the mortality group, with all differences reaching statistical significance(all P<0.05).Spearman correlation analysis indicated that urinary 8-oxoGuo levels were positively correlated with both PCT and SOFA scores in frail elderly sepsis patients( r=0.426, 0.768, both P<0.05).Furthermore, logistic regression analysis identified urinary 8-oxoGuo and SOFA as independent risk factors for 28-day mortality in this population( OR=1.936, 1.427; P=0.006, 0.002).The area under the receiver operating characteristic curve(AUC)for urinary 8-oxoGuo and SOFA in predicting the 28-day prognosis of frail elderly sepsis patients was 0.761 and 0.741, respectively, both demonstrating statistical significance(both P<0.001). Conclusions:Our findings suggest that urinary 8-oxoGuo possesses strong predictive value for the short-term prognosis of sepsis in this vulnerable population.

Objective To systematically retrieve,assess and synthesise regarding the respiratory training for patients with spinal cord injury and to provide a reference for clinical practice.Methods According to the 6S Evidence Pyramid Model,following databases were searched for literature in relation to the respiratory training for patients with spinal cord injury:UpToDate,BMJ Best Practice,Joanna Briggs Institute Database of Systematic Reviews and Implementations,National Institute for Health and Clinical Excellence(NICE),National Guideline Clearinghouse(NGC),Registered Nurses'Association of Ontario(RNAO),Medlive,American Spinal Injury Association(ASIA),Physiotherapy Evidence Database(PEDro),The Cochrane Library,PubMed,Web of Science,CNKI,Wanfang Data,SinoMed and the websites of the Journals published by Chinese Medical Association.The types of literature included clinical decisions,practice guidelines,expert consensus,evidence summaries,systematic reviews/Meta-analyses,and original researches.The search period was from the inception of databases to 30th December,2023.Two researchers independently evaluated the quality of the literature and summarised the evidences.Results Fifteen studies were ultimately included,comprising 3 clinical decisions,3 guidelines,6 systematic reviews and 3 randomised controlled trials.A total of 21 best pieces of evidence were summarised,covering 5 aspects:pre-training assessment,training content,training equipment,training intensity and frequency,and effectiveness evaluation.Conclusion The best evidence of respiratory training for patients with spinal cord injury summarised in this study can provide the evidence-based support for healthcare professionals to formulate standardised respiratory training strategies.

Objective:To investigate the significance of urinary 8-oxo-7, 8-dihydroguanosine(8-oxoGuo)in assessing the short-term prognosis of sepsis in frail elderly patients.Methods:We conducted a cross-sectional study involving 62 frail elderly patients diagnosed with sepsis who were admitted to the Emergency Intensive Care Unit(EICU)at Beijing Hospital between March 2021 and March 2022.Based on their 28-day prognosis, the patients were categorized into two groups: those who died and those who survived.Upon admission, we collected urine samples and clinical data from both groups.We employed isotope dilution high-performance liquid chromatography-mass spectrometry to measure the levels of the RNA oxidation marker 8-oxoGuo in the urine.Results:A total of 62 frail elderly patients[aged(85.1±6.3)years]diagnosed with sepsis were included in the study, comprising 36 patients in the 28-day mortality group and 26 patients in the survival group.Univariate analysis revealed that the survival group had significantly lower body temperature, blood calcitonin(PCT)levels, sequential organ failure assessment(SOFA)scores, and urinary 8-oxoGuo levels compared to the mortality group.Additionally, the survival group exhibited a higher mean arterial pressure(MAP)than the mortality group, with all differences reaching statistical significance(all P<0.05).Spearman correlation analysis indicated that urinary 8-oxoGuo levels were positively correlated with both PCT and SOFA scores in frail elderly sepsis patients( r=0.426, 0.768, both P<0.05).Furthermore, logistic regression analysis identified urinary 8-oxoGuo and SOFA as independent risk factors for 28-day mortality in this population( OR=1.936, 1.427; P=0.006, 0.002).The area under the receiver operating characteristic curve(AUC)for urinary 8-oxoGuo and SOFA in predicting the 28-day prognosis of frail elderly sepsis patients was 0.761 and 0.741, respectively, both demonstrating statistical significance(both P<0.001). Conclusions:Our findings suggest that urinary 8-oxoGuo possesses strong predictive value for the short-term prognosis of sepsis in this vulnerable population.

OBJECTIVE:Nowadays,machine learning algorithms are gradually being applied to predict stroke and cardiovascular disease.Compared with traditional regression models,machine learning can learn from data to achieve high prediction accuracy by exploring the flexible relationship between a large number of predictive features and outcome variables,providing a new method for the formulation of individualized treatment and rehabilitation programs.This study aims to systematically evaluate stroke functional recovery and prognosis prediction models based on machine learning,comprehensively assessing their predictive performance and clinical application potential to provide references for the development,application,and promotion of related predictive models.METHODS:This review was conducted following the PRISMA(Preferred Reporting Items for Systematic Reviews and Meta-Analyses)guidelines.Relevant literature on stroke prognosis prediction using machine learning methods was selected by searching PubMed,EMbase,Web of Science Core Collection,CNKI,WanFang,and the China Biomedical Literature Database,with the search period from January 1,2014,to July 1,2024.Two researchers independently screened the literature and extracted data based on inclusion and exclusion criteria,using the Prediction model Risk Of Bias ASsessment Tool(PROBAST)to assess model quality.RESULTS:(1)A total of 3 126 articles were obtained in the preliminary search.After screening and exclusion,18 articles were finally included.150 prediction models were constructed using 13 machine learning methods.The three most frequently used methods are Logistic Regression,Random Forest,and Extreme Gradient Boosting(XGBoost).Only one study was externally validated.Eight studies reported how the missing data were handled.(2)In terms of outcome indicators,8 studies used the combination of clinical data and imaging data to build models,9 studies only used clinical data to build models,and 1 study only used imaging data to build models.(3)Each of the 18 studies gave the most important characteristics of the study,with the most mentioned being the National Institute of Health Stroke Scale and age.All studies reported area under curve values ranging from 0.74 to 0.96,with the highest area under curve being 0.96.The overall risk of bias in all models was high.The high risk of bias in the field of model analysis was the main reason for the high risk of overall bias in all models.(4)The results of meta-analysis showed that age and National Institute of Health Stroke Scale score had significant influence on stroke prognosis,with age[MD=8.49,95％CI(6.24,10.75),P＜0.01]and National Institute of Health Stroke Scale score[MD=4.78,95％CI(2.56,7.00),P＜0.01].CONCLUSION:This study systematically evaluated the predictive model of functional recovery and prognosis of stroke based on machine learning,and all the models have good predictive potential.However,future studies should increase the sample size of the included model,adopt prospective studies,and add external validation of the model to improve the stability and prediction accuracy of the model,control the risk of bias,and contribute to the validation and promotion of the model in practical clinical applications.At the same time,the interpolation of missing values is more transparent and accurate.Although existing machine learning models show good predictive performance,it is also important to focus on the functionality and usability of the model,and the inclusion of features will reduce ease of use.We should develop easy to use model interfaces and user-friendly clinical tools to enable medical staff to better apply the model for clinical decision.

Objective To systematically retrieve,assess and synthesise regarding the respiratory training for patients with spinal cord injury and to provide a reference for clinical practice.Methods According to the 6S Evidence Pyramid Model,following databases were searched for literature in relation to the respiratory training for patients with spinal cord injury:UpToDate,BMJ Best Practice,Joanna Briggs Institute Database of Systematic Reviews and Implementations,National Institute for Health and Clinical Excellence(NICE),National Guideline Clearinghouse(NGC),Registered Nurses'Association of Ontario(RNAO),Medlive,American Spinal Injury Association(ASIA),Physiotherapy Evidence Database(PEDro),The Cochrane Library,PubMed,Web of Science,CNKI,Wanfang Data,SinoMed and the websites of the Journals published by Chinese Medical Association.The types of literature included clinical decisions,practice guidelines,expert consensus,evidence summaries,systematic reviews/Meta-analyses,and original researches.The search period was from the inception of databases to 30th December,2023.Two researchers independently evaluated the quality of the literature and summarised the evidences.Results Fifteen studies were ultimately included,comprising 3 clinical decisions,3 guidelines,6 systematic reviews and 3 randomised controlled trials.A total of 21 best pieces of evidence were summarised,covering 5 aspects:pre-training assessment,training content,training equipment,training intensity and frequency,and effectiveness evaluation.Conclusion The best evidence of respiratory training for patients with spinal cord injury summarised in this study can provide the evidence-based support for healthcare professionals to formulate standardised respiratory training strategies.

BACKGROUND:Early identification of patients requiring ventilator support will be beneficial for the outcomes of botulism.The present study aimed to establish a new scoring system to predict mechanical ventilation(MV)for botulism patients. METHODS:A single-center retrospective study was conducted to identify risk factors associated with MV in botulism patients from 2007 to 2022.Univariate analysis and multivariate logistic regression analysis were used to screen out risk factors for constructing a prognostic scoring system.The area under the receiver operating characteristic(ROC)curve was calculated. RESULTS:A total of 153 patients with botulism(66 males and 87 females,with an average age of 43 years)were included.Of these,49 patients(32.0%)required MV,including 21(13.7%)with invasive ventilation and 28(18.3%)with non-invasive ventilation.Multivariate analysis revealed that botulinum toxin type,pneumonia,incubation period,degree of hypoxia,and severity of muscle involvement were independent risk factors for MV.These risk factors were incorporated into a multivariate logistic regression analysis to establish a prognostic scoring system.Each risk factor was scored by allocating a weight based on its regression coefficient and rounded to whole numbers for practical utilization([botulinum toxin type A:1],[pneumonia:2],[incubation period≤1 day:2],[hypoxia<90%:2],[severity of muscle involvement:grade II,3;grade III,7;grade IV,11]).The scoring system achieved an area under the ROC curve of 0.82(95%CI 0.75-0.89,P<0.001).At the optimal threshold of 9,the scoring system achieved a sensitivity of 83.7%and a specificity of 70.2%. CONCLUSION:Our study identified botulinum toxin type,pneumonia,incubation period,degree of hypoxia,and severity of muscle involvement as independent risk factors for MV in botulism patients.A score≥9 in our scoring system is associated with a higher likelihood of requiring MV in botulism patients.This scoring system needs to be validated externally before it can be applied in clinical settings.

The detection rate of animal-derived low-dose antibiotics that reside in pregnant women's bodies is relatively high, and the cumulative effect impacts the establishment of the neonatal gut microbiota, leading to an imbalance in the microbial community structure. Exposure to low-dose antibiotics may have adverse effects on the health of pregnant women, fetuses, and newborns. This article reviews the impact of continuous low-dose antibiotic exposure during pregnancy on the establishment and colonization of neonatal gut microbiota, the alteration of the diversity of the neonatal gut microbiota, and the adverse effects on long-term growth and development.

Objective: To evaluate the value of multi-detector CT (MDCT) upper airway imaging in the diagnosis of obstructive sleep apnea hypopnea syndrome ( OSAHS) and in determining the location of upper airway obstruction． Methods : MDCT was used to scan the upper airways of 85 clinically confirmed adult patients with different degrees of OSAHS (73 males and 12 females) in calm breathing phase and forced inhalation phase and 60 normal adults (50 males and 10 females) in calm breathing phase to obtain nasal cavity，nasopharynx，palatopharynx and oglosopharynx volumes．Parapharyngeal fat volume was measured in OSAHS patients and normal subjects．In addition，three groups of clinical data related to OSAHS patients were recorded，including sleep apnea hypopnea index (AHI) ，body mass index ( BMI) and lowest blood oxygen saturation ( LaSO2 ) ．Finally，the measured data and clinical data of each group were statistically analyzed. Results : The volume of nasopharynx and palatopharynx in the calm breathing group was significantly smaller than that in the control group，with statistical significance．Palatopharyngeal volume forced inspiratory phase was significantly smaller than calm breathing phase in the experimental group．The parapharyngeal fat volume in the experimental group was significantly higher than that in the control group．AHI was positively correlated with BMI and parapharyngeal fat volume．LaSO2 was negatively correlated with AHI and BMI，respectively． Conclusion MDCT upper airway imaging has good clinical application value in the diagnosis，treatment and postoperative evaluation of OSAHS disease due to the significant anatomical difference between OSAHS patients and normal subjects.

Ulcerative colitis （UC） is a chronic intestinal disease with unknown etiology， with main symptoms of abdominal pain， diarrhea， mucus， pus， and blood in the stool. It can be accompanied by various complications and has a high risk of developing to colon cancer. In recent years， the incidence of UC and related colon cancer has been increasing， which seriously affects human health and quality of life. The operation， immunosuppressant， etc. are the main approaches in the modern clinical treatment of UC and related colon cancer， but these methods all have different toxic and side effects， and the therapeutic effect is not ideal. For many years， traditional Chinese medicine （TCM） has attracted much attention in the treatment of UC and related colon cancer due to its slightly toxic side effects and remarkable curative efficacy. Huangqintang， derived from the Shang Han Lun （伤寒论）， is composed of Scutellariae Radix， Paeoniae Radix Alba， Glycyrrhizae Radix et Rhizoma， and Jujubae Fructus with the functions of clearing heat， checking diarrhea， harmonizing the middle， and relieving pain， and has a significant effect on the treatment of UC. Huangqintang has complex compositions and plays roles with multiple targets and pathways. According to the literature and the research results of this research group for many years， it was found that the mechanism of Huangqintang in the treatment of UC and related colon cancer was presumably related to the protection of the intestinal mucosal barrier， inhibition of inflammatory response， promotion of mitophagy， inhibition of oxidative stress， regulation of intestinal flora， cell cycle， and gene expression， suppression of cell proliferation， and promotion of apoptosis. To provide theoretical references for an in-depth study of the mechanism and clinical use of Huangqintang， this paper reviewed the research advances in recent years.